Anomaly detection in time series data is a significant problem faced in many application areas such as manufacturing, medical imaging and cyber-security. Recently, Generative Adversarial Networks (GAN) have gained attention for generation and anomaly detection in image domain. In this paper, we propose a novel GAN-based unsupervised method called TAnoGan for detecting anomalies in time series when a small number of data points are available. We evaluate TAnoGan with 46 real-world time series datasets that cover a variety of domains. Extensive experimental results show that TAnoGan performs better than traditional and neural network models.
@article{arxiv.2008.09567,
title = {TAnoGAN: Time Series Anomaly Detection with Generative Adversarial Networks},
author = {Md Abul Bashar and Richi Nayak},
journal= {arXiv preprint arXiv:2008.09567},
year = {2021}
}
Comments
Made some minor changes. This is the accepted version of the paper at AusDM'20